Comments (6)
Hi,
You can download the 'rev' images. The link is in the README.md.
The images downloaded from Readme.me in the 'rev' have been flipped which you don't need to exchange the label.
from graphonomy.
@Gaoyiminggithub
I have ignored that. Thanks for your kind reply!
from graphonomy.
Sorry but I have another question......
In 'exp/transfer/train_cihp_from_pascal.py', there is a normalization applied to dataloader:
tr.Normalize_xception_tf(),
I do not know why you do this rather than standardizing them by: x-mean/std. Could you please tell me the difference between this two methods?
Thanks a lot!
from graphonomy.
Hi,
It is an interesting question.
Because the pretrained model is transferred from the Deeplab office code, the Deeplab code used the normalization way in here. So we use the same normalization way as it.
from graphonomy.
Moreover, you can use the normalization way like x-mean/std to train the base model.
from graphonomy.
I think the normalization method makes little effect to the final performance, right?
from graphonomy.
Related Issues (20)
- Train PASCAL from CIHP
- In the function Featuremaps_to_Graph,why softmax axis is -1?
- CUDA memory problem HOT 1
- How to fine-tune this model for a semantic segmentation task for human parsing ? HOT 2
- why actual performance is worse than deeplab v3+? HOT 2
- How to train and evaluate on deeplabv3 baseline? HOT 2
- why Inputs requires grad? HOT 1
- Closed
- No access to google drive HOT 1
- Universal trained model is in owner's trash
- where to get full pascal-part HOT 4
- Datasets license
- Universal weight is unavailable HOT 1
- Which was the model that generated the repo's messi_output.png HOT 1
- the Pascal pretrained model
- Access rights required
- Can only use the CPU?
- error will executing /inference.py Error PYTORCH_CUDA_ALLOC_CONF
- How to prepare the dataset?
- Issue with segmentation on images with 768X1024 resolution using Graphonomy
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from graphonomy.